1
$\begingroup$

this is my first post so let me know if you need more information. This is a pretty general question for now, but I am not sure how to approach this.
The data I have is from an ecological study. In this study, we had two different kind of experimental landscapes, landscape type A and B. We had 8 replicates for landscape type A and 4 replicates for landscape type B. The goal of the study was to compare dispersal of organisms between the two landscape types. Organisms were marked in the center of each landscape, released and recaptured at 4 different distances (i,ii,iii,iv) from the center. Now we want to know if we found significantly more organisms at a certain distance in either of the two landscape types. I don't think this would be too difficult, however, we don't know the number of the released organisms in each landscape. This said, we can't use the total numbers of recaptured organisms to compare the different landscapes but we have to use the percentages/proportions. The dataset for each landscape basically consists of 4 values (for the distances), which sum up to 100%. For example: At site A1, 20% of organisms were resampled at distance i, 25% at distance ii, 30% at distance iii, and 25% at distance iv. An additional caveat is that the dataset has a high number of 0% (distances, where no organism was resampled). Everything I came up with so far does not work for one or the other reason (glmm, zero inflated models, tobit...).
Does anybody have an idea how to approach this? I use R to perform the analyses.
Thanks in advance.
John

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.